system

Abstract

We provide the system. [Solution] A means for acquiring video data of the driver obtained from a video input means, A means for detecting and tracking the driver's face in real time based on the video data, A means for extracting features related to drowsiness from the detected driver's face, A means for estimating the driver's drowsiness level based on extracted features, A means for issuing a warning to the driver based on the estimation result, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Drowsiness of a driver is one of the main causes of traffic accidents, which may cause serious damage. However, conventional drowsiness detection systems have problems in real-time performance and accuracy, and it is difficult to give an accurate warning at the stage when a driver begins to feel drowsy. As a result, there is a demand to solve the problem that the risk of causing an accident without being aware of drowsiness during driving increases.

Means for Solving the Problems

[0005] This invention provides a system that acquires driver video data in real time and extracts features such as the driver's eye opening / closing state, blinking frequency, face orientation, and head tilt by performing face detection and tracking. Based on these features, the system estimates the driver's drowsiness level and issues a warning quickly based on the estimation result, thereby accurately detecting drowsiness and promoting safe driving.

[0006] "Video input means" refers to a device or function for acquiring video data from a camera, dashcam, or similar source.

[0007] "Driver face detection and tracking" is the process of identifying the driver's face from acquired video data and tracking its position and movement.

[0008] "Feature extraction" involves analyzing information that indicates drowsiness from the driver's face, extracting data such as the state of eye opening and closing, blinking frequency, face orientation, and head tilt.

[0009] "Drowsiness level estimation" is a process that uses mathematical models and algorithms to evaluate how drowsy a driver is feeling based on extracted features.

[0010] "Warning means" refers to a device or function that alerts the driver through audio or visual signals. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface that includes a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] The system of this invention consists of a terminal mounted in the vehicle and a server that performs analysis in a central location. The terminal includes a drive recorder, which includes a camera as a video input means for capturing images of the driver inside the vehicle. The video data is transmitted to the server in real time and analyzed there.

[0033] The server detects the driver's face from the received video data and continuously tracks the identified face. During this process, it extracts features such as the driver's eye opening / closing state, blinking frequency, face orientation, and head tilt. These features are treated as important data because they may indicate signs of drowsiness.

[0034] Based on the extracted features, a generative AI model on the server estimates the driver's drowsiness level. This estimate is quantified as a drowsiness score and compared to a set threshold. If the threshold is exceeded, the server sends a warning signal to the terminal.

[0035] The terminal receives warning signals from the server and issues warnings to the user (driver) in an audible or visual manner. For example, this can be done using voice alerts or warning displays on the dashboard. This helps the user become aware of drowsiness and encourages them to take a break at an appropriate time.

[0036] For example, if the system detects an increase in the driver's blinking frequency while driving on a highway for extended periods, it can immediately issue a warning, alerting the driver to the long time since their last break and encouraging them to take a safe rest.

[0037] Such a system can reduce the risk of accidents caused by drowsiness while driving and provide a safer driving environment.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The device acquires video data via the in-car camera. The acquired video data is transmitted to the server in real time.

[0041] Step 2:

[0042] The server detects the driver's face from the received video data. To perform face detection, a machine learning algorithm is applied to identify the location of the person's face in the video.

[0043] Step 3:

[0044] The server tracks the identified face. It continuously tracks facial movements and corrects for changes in face size and position to obtain stable data.

[0045] Step 4:

[0046] The server extracts features from the facial tracking results. It extracts data that serves as an indicator for determining drowsiness, such as the state of eye opening and closing, blinking frequency, face direction, and head tilt.

[0047] Step 5:

[0048] The server estimates the drowsiness level based on the extracted features. A generative AI model is used to analyze the features and calculate a drowsiness score.

[0049] Step 6:

[0050] The server calculates a drowsiness score and compares it to a set threshold. If the score exceeds the threshold, it is determined that there are signs of drowsiness.

[0051] Step 7:

[0052] If the server detects signs of drowsiness, it sends a warning signal to the terminal.

[0053] Step 8:

[0054] The device issues a warning to the user based on the warning signal it receives. The warning is given using audio alerts or visual displays. The user receives the warning and is prompted to stop the vehicle and take a break if necessary.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] During long drives or in monotonous road conditions, drivers can easily become drowsy. However, drowsiness can lead to delayed reactions and falling asleep at the wheel, increasing the risk of serious traffic accidents. Therefore, there is a need for methods to maintain safe driving by detecting drowsiness early and providing appropriate warnings to drivers.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for collecting video information of vehicle users obtained from a video acquisition device, means for continuously recognizing and tracking the faces of vehicle users based on the video information, and means for extracting characteristic information related to drowsiness from the faces of recognized vehicle users. This makes it possible to quickly and accurately detect signs of drowsiness while driving and to immediately issue a warning to the driver.

[0060] A "video acquisition device" is a device installed inside or outside a vehicle to collect image information of the driver.

[0061] "Vehicle user" refers to an individual who operates or uses a vehicle, and in this invention, it primarily means the driver.

[0062] "Video information" refers to image data obtained by video acquisition devices, and is fundamental data for analyzing the driver's actions and behavior.

[0063] "Recognition and tracking" refers to the technology of detecting a specific object from collected video information and continuously analyzing its location and movement.

[0064] "Characteristic information" refers to measurable data related to the driver's level of drowsiness and attention, extracted from the driver's video footage, and includes, for example, eye opening and closing patterns and blinking frequency.

[0065] "Means for evaluating drowsiness" refers to a function that quantifies and estimates the driver's current level of attention and alertness based on extracted characteristic information.

[0066] A "warning" is a visual or audible notification signal issued to draw the driver's attention.

[0067] An embodiment of this invention is a system consisting of a terminal mounted in a vehicle and a central server. The terminal functions as a video acquisition device and collects video information of vehicle users. For example, a camera installed inside the vehicle may be used as the terminal. This camera captures the driver's face and upper body and acquires video data in real time. The terminal transmits this data to the server via Wi-Fi or mobile communication.

[0068] The server analyzes the transmitted video information using open-source image processing libraries. First, it detects the faces of vehicle users from the video information and continuously tracks them using a specific algorithm. Face landmark detection technology is utilized for face recognition and tracking. Next, the server extracts feature information based on the movement and state of the face. This feature information is an important indicator for evaluating driver drowsiness and includes specific data such as eye opening and closing and head tilt.

[0069] Based on the extracted feature information, the server uses a generative AI model to evaluate the driver's drowsiness level. This AI model is pre-trained using machine learning and can estimate the likelihood of drowsiness with high accuracy. If the evaluated drowsiness score exceeds a set threshold, the server sends an alert to the terminal. This alert is communicated to the user via acoustic or visual signals. For example, an audio alert may be played from the speaker, or a message such as "Please be careful" may be displayed on the dashboard display.

[0070] An example of a prompt message would be, "Detect the driver's face from the video data while driving and analyze signs of drowsiness." This allows the system to monitor the driver's condition and improve driving safety.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The terminal acquires real-time video data of the driver using a camera installed inside the vehicle. The camera's angle is adjusted to capture the driver's face and upper body. The input consists of continuous image frames acquired from the camera sensor. The output is video data ready for transmission to the server.

[0074] Step 2:

[0075] The terminal transmits the acquired video data to the server via the network. Wi-Fi or cellular communication is used for communication, and the data may be temporarily buffered. The input is the video data obtained in step 1, and the output is the video data received by the server.

[0076] Step 3:

[0077] The server detects the driver's face from the received video data. Here, a video processing library is used to recognize the facial contours and landmarks. The input is video data transmitted from the terminal, and the output is data containing facial position information. Specifically, an image analysis algorithm is applied.

[0078] Step 4:

[0079] The server extracts feature information such as eye opening / closing status, blinking frequency, face orientation, and head tilt from the detected face location data. This process analyzes variations between frames and extracts specific patterns. The input is face location data, and the output is feature information used for drowsiness estimation.

[0080] Step 5:

[0081] The server inputs the extracted feature information into a generating AI model to estimate the driver's drowsiness level. The AI ​​model generates a drowsiness score based on pre-trained data. The input is feature information, and the output is data quantified as a drowsiness score.

[0082] Step 6:

[0083] The server compares the estimated drowsiness score to a set threshold and sends an alarm signal to the terminal if necessary. Here, the threshold is pre-set as a threshold to maintain safe driving. The input is the drowsiness score, and the output is the instruction to send an alarm signal.

[0084] Step 7:

[0085] The terminal receives alarm signals from the server and issues warnings to the user (driver) via audio and visual signals. These warnings may include messages displayed on the dashboard or alerts from the speaker. The input is the alarm signal from the server, and the output is the alarm perceived by the user.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] In today's traffic society, accidents caused by driver drowsiness remain a serious problem. To address this issue, there is a need for technology that can monitor drivers' conditions in real time, predict drowsiness, and prompt them to take appropriate breaks. Furthermore, there is a lack of information available to help drivers take breaks efficiently. A system that solves this problem is needed.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for acquiring video data of the driver obtained from a video input means, means for detecting and tracking the driver's face in real time based on the video data, means for extracting features related to drowsiness from the detected driver's face, and means for suggesting the next rest stop based on the driver's state. This makes it possible to reduce the risk of accidents caused by driver drowsiness and provide information to enable the driver to rest efficiently.

[0091] "Video input means" refers to a device or method used to acquire video data of the driver.

[0092] A "device that detects and tracks the driver's face in real time" is a technology that continuously identifies the position and movement of the driver's face in real time based on video data of the driver.

[0093] "Characteristics related to drowsiness" refer to facial features and movements that may suggest drowsiness, such as the state of the driver's eyes (open and closed), blinking frequency, face orientation, and head tilt.

[0094] A "device for estimating a driver's drowsiness level" is a system that analyzes extracted features to determine the driver's level of drowsiness.

[0095] A "warning device" is a means of providing a signal to the driver to alert them based on an estimated level of drowsiness.

[0096] A "device that suggests the next rest stop based on the driver's condition" is an information provision system that takes into account the driver's current level of drowsiness and shows the driver the optimal rest location and time.

[0097] To implement this invention, a system is required that utilizes a terminal mounted on the vehicle and a server for analysis. The terminal includes a camera as a means of video input and acquires video data of the driver. This data is transmitted to the server in real time. The server uses a generated AI model to detect the driver's face from the received video data and tracks it in real time. Through face tracking, features related to drowsiness are extracted, including the state of eye opening and closing, blinking frequency, face orientation, and head tilt.

[0098] The server runs a generative AI model that estimates the driver's drowsiness level based on these features. If the estimated drowsiness level exceeds a threshold, the server sends a warning signal to the terminal. This warning is communicated to the driver using audio and visual signals.

[0099] The system also includes a feature that suggests the next rest stop based on the driver's level of drowsiness. The server calculates the optimal rest stop based on location and road information and provides this information to the device. This information is displayed on the driver's smartphone or the vehicle's display.

[0100] For example, if a driver blinks more frequently while driving for an extended period, the server will determine that the driver is becoming drowsy. In this case, a message such as, "You appear to be tired while driving. How about taking a break at the next rest stop?" can be sent to the terminal, and a nearby service area can be displayed on the map to encourage the driver to take a break.

[0101] Examples of prompt statements include the following:

[0102] "Design a system that analyzes driver drowsiness in real time and prompts rest as needed."

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The terminal uses a camera installed inside the vehicle to acquire video data of the driver. The video data is transmitted to the server in real time. The input is the raw video from the camera, and the output is the digital video data transmitted to the server.

[0106] Step 2:

[0107] The server analyzes the received video data and uses a generative AI model to detect the driver's face. The AI ​​model has a pre-installed face recognition algorithm that extracts specific facial features from the video data. The input is video data, and the output is a dataset containing the face detection results.

[0108] Step 3:

[0109] The server extracts features related to drowsiness from the detected faces. Specifically, it uses an AI model to calculate eye open / closed states, blinking frequency, face orientation, and head tilt. The input is the face detection result, and the output is data containing these features.

[0110] Step 4:

[0111] The server estimates the driver's drowsiness level based on extracted features. The AI ​​model evaluates multiple features and calculates a drowsiness score. The input is feature data, and the output is the drowsiness score.

[0112] Step 5:

[0113] If the generated drowsiness score exceeds a set threshold, the server sends a warning signal to the terminal. This includes a trigger signal to alert the driver. The input is the drowsiness score, and the output is the warning signal.

[0114] Step 6:

[0115] The device uses the received warning signal to send audio and visual warnings to the driver. Specific actions include outputting an audio alert from the speaker and displaying a warning message on the screen. The input is the warning signal, and the output is feedback to the user.

[0116] Step 7:

[0117] The server calculates information about the next rest stop based on the driver's current drowsiness level and sends it to the terminal. This involves combining GPS data and road information to determine an appropriate rest stop. The input is drowsiness level and location information, and the output is suggested rest stop information.

[0118] Step 8:

[0119] The device notifies the driver of the received rest stop information and displays accessible rest stops on a map. Specifically, it displays a map showing rest stops on the smartphone or vehicle's display. The input is suggested rest stop information, and the output is visual information for the user.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] This invention provides a system that accurately detects a driver's drowsiness and emotional state, thereby supporting safe driving. The system consists of a terminal installed in the vehicle and a server that analyzes video data.

[0122] The terminal uses the vehicle's cameras to acquire video data of the driver. This video data is transmitted to the server in real time. Based on the received video data, the server detects and continuously tracks the driver's face. In this process, features related to drowsiness, such as eye opening and closing, blinking frequency, face orientation, and head tilt, are extracted.

[0123] Furthermore, the server is equipped with an emotion engine that analyzes the driver's facial expression data to determine their emotional state. This emotion recognition evaluates the driver's emotions, such as joy, surprise, anger, sadness, and stress. The emotion engine then comprehensively evaluates this information to infer the driver's attention level and psychological state.

[0124] Based on the extracted features and sentiment analysis results, the server estimates the driver's drowsiness level and issues an immediate warning if necessary. The warning is adjusted according to the driver's emotional state; for example, if the driver is stressed, a milder warning will be issued.

[0125] For example, if the driver's eyes start opening and closing slowly during long-distance driving, and they also appear irritated, the system will provide a voice and display warning such as, "Drowsiness has been detected. Please take a short break and relax." This allows the driver to recognize their condition early and take appropriate actions for safe driving.

[0126] In this way, the system can comprehensively monitor the driver's drowsiness and emotions, providing a safety function that helps prevent traffic accidents.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The terminal uses cameras installed inside the vehicle to acquire video data of the driver. This video data is transmitted to the server in real time.

[0130] Step 2:

[0131] The server uses a face detection algorithm to identify the driver's face from the received video data. The identified face is then tracked to stably acquire continuous data.

[0132] Step 3:

[0133] The server extracts features such as eye opening / closing status, blinking frequency, face orientation, and head tilt from the face it tracks. This data is used to analyze drowsiness.

[0134] Step 4:

[0135] The server uses an emotion engine to analyze the driver's emotional state from their facial expressions. This analysis evaluates emotions such as joy, surprise, anger, sadness, and stress that the driver is experiencing.

[0136] Step 5:

[0137] The server estimates the driver's drowsiness level based on extracted features and sentiment analysis results. It then checks whether the drowsiness score exceeds a pre-set threshold.

[0138] Step 6:

[0139] The server creates the most appropriate warning for the driver based on the estimated drowsiness score and emotional state. If the result is deemed dangerous, a warning signal is sent to the terminal.

[0140] Step 7:

[0141] The terminal receives a warning signal from the server and issues a warning to the user. The warning is delivered via audio or visual means, and its content is tailored to best suit the driver's condition.

[0142] (Example 2)

[0143] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0144] During long drives or in monotonous driving environments, driver drowsiness and psychological fatigue are often contributing factors to accidents. However, conventional systems are insufficient to accurately monitor drowsiness and emotional states and provide timely warnings to drivers. Therefore, there is a need for a system that can detect driver drowsiness and emotional states with high accuracy and support safe driving.

[0145] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0146] In this invention, the server includes means for analyzing and tracking the driver's video information in real time, means for extracting drowsiness-related feature data from the driver's face, and means for analyzing the emotional state from the facial expression data. This makes it possible to estimate the driver's drowsiness level and emotional state with high accuracy and issue appropriate warnings.

[0147] A "video input device" is a device used to acquire video information of the driver and has the function of providing video data in real time.

[0148] "Analysis" refers to the process of determining the driver's condition based on video information and facial expression data.

[0149] "Tracking" is a technology that monitors the driver's posture and behavior by continuously tracking detected facial movements.

[0150] "Characteristic data" refers to specific data related to drowsiness and the driver's condition, such as eye opening and closing, blinking frequency, face orientation, and head tilt.

[0151] "Drowsiness level" is an index that quantifies or grades the driver's level of alertness.

[0152] "Facial expression data" refers to information about the driver's facial expressions, which is used to determine their emotional state.

[0153] "Emotional state" refers to the driver's mental reactions and psychological condition, including joy, surprise, anger, sadness, and stress.

[0154] A "warning" refers to an audible or visual signal issued to draw the driver's attention or provide advice.

[0155] This invention is a system for detecting the drowsiness and emotional state of a vehicle driver with high accuracy and supporting safe driving. This system consists of a terminal installed inside the vehicle and a server that analyzes video data.

[0156] The terminal acquires video information of the driver using the vehicle's cameras. For this purpose, it uses a high-resolution camera mounted on the terminal. The camera records video data in real time and transmits it to a server via a high-speed communication network such as Wi-Fi or 5G.

[0157] The server uses the received video data and an AI facial recognition library to identify and continuously track the driver's face. Libraries such as OpenCV and Dlib are used in this process. The server then extracts drowsiness-related feature data, such as eye opening / closing status, blinking frequency, face orientation, and head tilt.

[0158] Furthermore, the server is equipped with an emotion recognition engine that uses a deep learning model to analyze the driver's emotional state from facial expression data. Frameworks such as TENSORFLOW® and PyTorch are commonly used. Emotion analysis is performed to evaluate the driver's psychological state, including joy, surprise, anger, sadness, and stress.

[0159] By comprehensively analyzing this data, the server estimates the driver's level of drowsiness and issues a warning if necessary. The warning is generated using speech synthesis technology and communicated to the driver audibly or visually. For example, if the driver blinks slowly and shows signs of stress during long-distance driving, the server will warn, "Drowsiness detected. Please take a short break and relax."

[0160] An example of a prompt to a generative AI model is: "Please tell me how to analyze the driver's eye opening / closing state and facial expression based on image data to evaluate drowsiness and emotional state."

[0161] In this way, the system of the present invention can monitor the driver's condition with high precision and provide a safety function that prevents traffic accidents.

[0162] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0163] Step 1:

[0164] The terminal acquires video information of the driver through a camera installed inside the vehicle. The camera is adjusted to capture the driver's face clearly at high resolution. The input is raw video data acquired by the camera, which is then encoded and converted to an appropriate format. The output is video data in a transmittable format.

[0165] Step 2:

[0166] The device sends encoded video data to the server. This communication takes place using a Wi-Fi or 5G network, and the data is transferred with low latency. The input is the encoded video data, and the output is the video data delivered to the server.

[0167] Step 3:

[0168] The server analyzes the video data received from the terminal and detects the driver's face using AI facial recognition software. An open-source facial recognition library is used to extract the face's location information. The input is the received video data, and the output is the driver's face location information.

[0169] Step 4:

[0170] The server tracks detected facial movements and extracts sleepiness-related feature data such as eye opening / closing status, blinking frequency, face orientation, and head tilt. Image processing libraries are used for this process. The input is facial position information, and the output is sleepiness-related feature data.

[0171] Step 5:

[0172] The server analyzes the driver's emotional state based on extracted feature data. It uses a deep learning model to classify emotions from facial expression data. The input is feature data, and the output is information about the emotional state.

[0173] Step 6:

[0174] The server comprehensively evaluates the driver's drowsiness level and emotional state, and generates a warning to the driver as needed. Natural language processing techniques are used for this warning generation. The input is the drowsiness level and emotional state, and the output is a warning message to the driver.

[0175] Step 7:

[0176] Warning messages sent from the server are notified to the user via the terminal. The warning messages are played aloud using speech synthesis technology. The input is the warning message, and the output is either an audio or visual warning.

[0177] (Application Example 2)

[0178] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0179] Responding quickly to driver drowsiness and changes in emotional state to support safe driving is a crucial challenge. In particular, it is necessary to adjust the environment appropriately according to the driver's psychological state to reduce fatigue and stress. Conventional systems have the problem that they can only monitor drowsiness and emotional state individually, making it difficult to provide comprehensive safe driving support.

[0180] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0181] In this invention, the server includes means for acquiring video information of the operator from a video input device, means for detecting and tracking the operator's face in real time based on the video information, means for extracting characteristic information related to drowsiness from the detected operator's face, and means for adjusting the environment based on the operator's emotional state. This makes it possible to comprehensively judge the driver's drowsiness and emotional state in real time and provide appropriate warnings and environmental adjustments.

[0182] A "video input device" is a device that captures the operator's face and surrounding environment in real time and acquires that video information.

[0183] "Operator" refers to a person who operates a vehicle or machine.

[0184] "Tracking" refers to the continuous monitoring of the detected face's position and movement.

[0185] "Characteristic information" refers to specific data extracted from the pilot's face that indicates drowsiness and emotional state.

[0186] "Sleepiness level" refers to the pilot's state of alertness and is a scale used to assess how much attention is required in that state.

[0187] "Notification" refers to the act of a system communicating warnings or information to the operator through audio or video.

[0188] "Environmental adjustment" refers to modifying environmental elements such as the sound and lighting inside the vehicle according to the driver's psychological state.

[0189] To implement this invention, it is necessary to acquire video footage of the driver using a camera placed inside the vehicle and transmit that data to a server. The server uses OpenCV as its video processing library to perform real-time facial recognition and tracking of the driver. Furthermore, it extracts features and analyzes the driver's emotional state using an emotion analysis API such as AWS® Rekognition. Based on this data, the server estimates the driver's level of drowsiness and emotional state and issues a warning as needed.

[0190] Furthermore, the in-vehicle infotainment system automatically adjusts the sound and lighting according to the driver's state. This program helps reduce stress while driving and supports safe driving.

[0191] For example, if the driver's blinking frequency increases during long-distance driving and emotional analysis detects fatigue, the system will issue a voice warning saying, "Take a short break and refresh yourself." It can also change the interior lighting to a softer color and play relaxing music.

[0192] An example of a prompt message might be: "Please write a program that analyzes the pilot's drowsiness and emotions in real time using video data, and generates rest suggestions based on the pilot's condition."

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The terminal uses a camera installed inside the vehicle to capture video of the driver. The input is the camera feed, and the output is this video data. At this stage, the video is captured in real time.

[0196] Step 2:

[0197] The server receives video data transmitted from the terminal. The input is the video data from the terminal, and the output is the video data prepared for analysis. In this process, the server verifies the integrity of the data transfer.

[0198] Step 3:

[0199] The server uses OpenCV to detect and track the operator's face in real time from video data. The input is video data, and the output is the operator's facial feature points. This process involves identifying the detected coordinates of the face and continuously tracking it.

[0200] Step 4:

[0201] The server extracts sleepiness-related feature information from the detected faces. The input is facial feature points, and the output is information such as eye open / closed state and blinking frequency. This process generates specific indicators of sleepiness.

[0202] Step 5:

[0203] The server uses an emotion analysis API to analyze the operator's emotional state from extracted facial data. The input is facial feature information, and the output is the operator's emotional state. Here, the emotion engine identifies states such as joy and stress.

[0204] Step 6:

[0205] The server comprehensively assesses the degree of drowsiness and emotional state, and issues notifications to the pilot as needed. Input is information about drowsiness and emotions, and output is the notification content. If a warning is required, it will be communicated to the pilot via voice or display.

[0206] Step 7:

[0207] The server adjusts the in-vehicle environment (sound and lighting) according to the driver's state. The input is the driver's emotional state, and the output is the adjusted environmental settings. This process optimizes the environment to improve driving comfort.

[0208] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0209] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0210] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0214] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0215] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0216] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0217] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0218] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0219] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0220] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0221] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0222] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0223] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0224] The system of this invention consists of a terminal mounted in the vehicle and a server that performs analysis in a central location. The terminal includes a drive recorder, which includes a camera as a video input means for capturing images of the driver inside the vehicle. The video data is transmitted to the server in real time and analyzed there.

[0225] The server detects the driver's face from the received video data and continuously tracks the identified face. During this process, it extracts features such as the driver's eye opening / closing state, blinking frequency, face orientation, and head tilt. These features are treated as important data because they may indicate signs of drowsiness.

[0226] Based on the extracted features, a generative AI model on the server estimates the driver's drowsiness level. This estimate is quantified as a drowsiness score and compared to a set threshold. If the threshold is exceeded, the server sends a warning signal to the terminal.

[0227] The terminal receives warning signals from the server and issues warnings to the user (driver) in an audible or visual manner. For example, this can be done using voice alerts or warning displays on the dashboard. This helps the user become aware of drowsiness and encourages them to take a break at an appropriate time.

[0228] For example, if the system detects an increase in the driver's blinking frequency while driving on a highway for extended periods, it can immediately issue a warning, alerting the driver to the long time since their last break and encouraging them to take a safe rest.

[0229] Such a system can reduce the risk of accidents caused by drowsiness while driving and provide a safer driving environment.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The device acquires video data via the in-car camera. The acquired video data is transmitted to the server in real time.

[0233] Step 2:

[0234] The server detects the driver's face from the received video data. To perform face detection, a machine learning algorithm is applied to identify the location of the person's face in the video.

[0235] Step 3:

[0236] The server tracks the identified face. It continuously tracks facial movements and corrects for changes in face size and position to obtain stable data.

[0237] Step 4:

[0238] The server extracts features from the facial tracking results. It extracts data that serves as an indicator for determining drowsiness, such as the state of eye opening and closing, blinking frequency, face direction, and head tilt.

[0239] Step 5:

[0240] The server estimates the drowsiness level based on the extracted features. A generative AI model is used to analyze the features and calculate a drowsiness score.

[0241] Step 6:

[0242] The server calculates a drowsiness score and compares it to a set threshold. If the score exceeds the threshold, it is determined that there are signs of drowsiness.

[0243] Step 7:

[0244] If the server detects signs of drowsiness, it sends a warning signal to the terminal.

[0245] Step 8:

[0246] The device issues a warning to the user based on the warning signal it receives. The warning is given using audio alerts or visual displays. The user receives the warning and is prompted to stop the vehicle and take a break if necessary.

[0247] (Example 1)

[0248] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0249] During long drives or in monotonous road conditions, drivers can easily become drowsy. However, drowsiness can lead to delayed reactions and falling asleep at the wheel, increasing the risk of serious traffic accidents. Therefore, there is a need for methods to maintain safe driving by detecting drowsiness early and providing appropriate warnings to drivers.

[0250] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0251] In this invention, the server includes means for collecting video information of vehicle users obtained from a video acquisition device, means for continuously recognizing and tracking the faces of vehicle users based on the video information, and means for extracting characteristic information related to drowsiness from the faces of recognized vehicle users. This makes it possible to quickly and accurately detect signs of drowsiness while driving and to immediately issue a warning to the driver.

[0252] A "video acquisition device" is a device installed inside or outside a vehicle to collect image information of the driver.

[0253] "Vehicle user" refers to an individual who operates or uses a vehicle, and in this invention, it primarily means the driver.

[0254] "Video information" refers to image data obtained by video acquisition devices, and is fundamental data for analyzing the driver's actions and behavior.

[0255] "Recognition and tracking" refers to the technology of detecting a specific object from collected video information and continuously analyzing its location and movement.

[0256] "Characteristic information" refers to measurable data related to the driver's level of drowsiness and attention, extracted from the driver's video footage, and includes, for example, eye opening and closing patterns and blinking frequency.

[0257] "Means for evaluating drowsiness" refers to a function that quantifies and estimates the driver's current level of attention and alertness based on extracted characteristic information.

[0258] A "warning" is a visual or audible notification signal issued to draw the driver's attention.

[0259] An embodiment of this invention is a system consisting of a terminal mounted in a vehicle and a central server. The terminal functions as a video acquisition device and collects video information of vehicle users. For example, a camera installed inside the vehicle may be used as the terminal. This camera captures the driver's face and upper body and acquires video data in real time. The terminal transmits this data to the server via Wi-Fi or mobile communication.

[0260] The server analyzes the transmitted video information using open-source image processing libraries. First, it detects the faces of vehicle users from the video information and continuously tracks them using a specific algorithm. Face landmark detection technology is utilized for face recognition and tracking. Next, the server extracts feature information based on the movement and state of the face. This feature information is an important indicator for evaluating driver drowsiness and includes specific data such as eye opening and closing and head tilt.

[0261] Based on the extracted feature information, the server uses a generative AI model to evaluate the driver's drowsiness level. This AI model is pre-trained using machine learning and can estimate the likelihood of drowsiness with high accuracy. If the evaluated drowsiness score exceeds a set threshold, the server sends an alert to the terminal. This alert is communicated to the user via acoustic or visual signals. For example, an audio alert may be played from the speaker, or a message such as "Please be careful" may be displayed on the dashboard display.

[0262] An example of a prompt message would be, "Detect the driver's face from the video data while driving and analyze signs of drowsiness." This allows the system to monitor the driver's condition and improve driving safety.

[0263] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0264] Step 1:

[0265] The terminal acquires real-time video data of the driver using a camera installed inside the vehicle. The camera's angle is adjusted to capture the driver's face and upper body. The input consists of continuous image frames acquired from the camera sensor. The output is video data ready for transmission to the server.

[0266] Step 2:

[0267] The terminal transmits the acquired video data to the server via the network. Wi-Fi or cellular communication is used for communication, and the data may be temporarily buffered. The input is the video data obtained in step 1, and the output is the video data received by the server.

[0268] Step 3:

[0269] The server detects the driver's face from the received video data. Here, a video processing library is used to recognize the facial contours and landmarks. The input is video data transmitted from the terminal, and the output is data containing facial position information. Specifically, an image analysis algorithm is applied.

[0270] Step 4:

[0271] The server extracts feature information such as eye opening / closing status, blinking frequency, face orientation, and head tilt from the detected face location data. This process analyzes variations between frames and extracts specific patterns. The input is face location data, and the output is feature information used for drowsiness estimation.

[0272] Step 5:

[0273] The server inputs the extracted feature information into a generating AI model to estimate the driver's drowsiness level. The AI ​​model generates a drowsiness score based on pre-trained data. The input is feature information, and the output is data quantified as a drowsiness score.

[0274] Step 6:

[0275] The server compares the estimated drowsiness score to a set threshold and sends an alarm signal to the terminal if necessary. Here, the threshold is pre-set as a threshold to maintain safe driving. The input is the drowsiness score, and the output is the instruction to send an alarm signal.

[0276] Step 7:

[0277] The terminal receives alarm signals from the server and issues warnings to the user (driver) via audio and visual signals. These warnings may include messages displayed on the dashboard or alerts from the speaker. The input is the alarm signal from the server, and the output is the alarm perceived by the user.

[0278] (Application Example 1)

[0279] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0280] In modern transportation society, accidents caused by driver fatigue are still serious problems. To address this issue, there is a need for technologies that can monitor the driver's condition in real time, predict fatigue, and appropriately prompt rest. Additionally, there is a lack of information provision to enable drivers to take efficient rest. There is a need to provide a system to solve this problem.

[0281] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0282] In this invention, the server includes means for acquiring driver video data obtained from video input means, means for detecting and tracking the driver's face in real time based on the video data, means for extracting feature quantities related to fatigue from the detected driver's face, and means for proposing the next rest point based on the driver's condition. Thereby, it becomes possible to reduce the risk of accidents caused by driver fatigue and provide information for the driver to take efficient rest.

[0283] The "video input means" is a device or method used to acquire driver video data.

[0284] The "device for detecting and tracking the driver's face in real time" is a technology for continuously identifying the position and movement of the face in real time based on driver video data.

[0285] The "feature quantities related to fatigue" are facial features and movements that may suggest fatigue, such as the opening and closing state of the driver's eyes, the frequency of blinking, the direction of the face, and the tilt of the head.

[0286] The "device for estimating the driver's fatigue state" is a system for analyzing the extracted feature quantities and determining the driver's fatigue level.

[0287] The "device for issuing a warning" is a means for providing a signal to prompt the driver's attention based on the estimation result of fatigue.

[0288] A "device that suggests the next rest stop based on the driver's condition" is an information provision system that takes into account the driver's current level of drowsiness and shows the driver the optimal rest location and time.

[0289] To implement this invention, a system is required that utilizes a terminal mounted on the vehicle and a server for analysis. The terminal includes a camera as a means of video input and acquires video data of the driver. This data is transmitted to the server in real time. The server uses a generated AI model to detect the driver's face from the received video data and tracks it in real time. Through face tracking, features related to drowsiness are extracted, including the state of eye opening and closing, blinking frequency, face orientation, and head tilt.

[0290] The server runs a generative AI model that estimates the driver's drowsiness level based on these features. If the estimated drowsiness level exceeds a threshold, the server sends a warning signal to the terminal. This warning is communicated to the driver using audio and visual signals.

[0291] The system also includes a feature that suggests the next rest stop based on the driver's level of drowsiness. The server calculates the optimal rest stop based on location and road information and provides this information to the device. This information is displayed on the driver's smartphone or the vehicle's display.

[0292] For example, if a driver blinks more frequently while driving for an extended period, the server will determine that the driver is becoming drowsy. In this case, a message such as, "You appear to be tired while driving. How about taking a break at the next rest stop?" can be sent to the terminal, and a nearby service area can be displayed on the map to encourage the driver to take a break.

[0293] Examples of prompt statements include the following:

[0294] "Design a system that analyzes driver drowsiness in real time and prompts rest as needed."

[0295] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0296] Step 1:

[0297] The terminal uses a camera installed inside the vehicle to acquire video data of the driver. The video data is transmitted to the server in real time. The input is the raw video from the camera, and the output is the digital video data transmitted to the server.

[0298] Step 2:

[0299] The server analyzes the received video data and uses a generative AI model to detect the driver's face. The AI ​​model has a pre-installed face recognition algorithm that extracts specific facial features from the video data. The input is video data, and the output is a dataset containing the face detection results.

[0300] Step 3:

[0301] The server extracts features related to drowsiness from the detected faces. Specifically, it uses an AI model to calculate eye open / closed states, blinking frequency, face orientation, and head tilt. The input is the face detection result, and the output is data containing these features.

[0302] Step 4:

[0303] The server estimates the driver's drowsiness level based on extracted features. The AI ​​model evaluates multiple features and calculates a drowsiness score. The input is feature data, and the output is the drowsiness score.

[0304] Step 5:

[0305] If the generated drowsiness score exceeds a set threshold, the server sends a warning signal to the terminal. This includes a trigger signal to alert the driver. The input is the drowsiness score, and the output is the warning signal.

[0306] Step 6:

[0307] Based on the received warning signal, the terminal issues an audible or visual warning to the driver. Specific actions include outputting an audible alert from the speaker and displaying a warning message on the display. The input is the warning signal, and the output is the feedback to the user.

[0308] Step 7:

[0309] Based on the driver's current drowsiness state, the server calculates the information of the next rest stop and transmits it to the terminal. This involves combining GPS data and road information to determine an appropriate rest stop. The input is the drowsiness state and location information, and the output is the proposed information of the rest stop.

[0310] Step 8:

[0311] The terminal notifies the driver of the received rest stop information and displays the accessible rest places on the map. As a specific action, it displays a map indicating the rest stop on the smartphone or the vehicle's display. The input is the proposed information of the rest stop, and the output is the visual information to the user.

[0312] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0313] The present invention provides a system that accurately detects the driver's drowsiness and emotional state and supports safe driving. This system is composed of a terminal installed in the vehicle and a server that analyzes video data.

[0314] The terminal uses the vehicle's cameras to acquire video data of the driver. This video data is transmitted to the server in real time. Based on the received video data, the server detects and continuously tracks the driver's face. In this process, features related to drowsiness, such as eye opening and closing, blinking frequency, face orientation, and head tilt, are extracted.

[0315] Furthermore, the server is equipped with an emotion engine that analyzes the driver's facial expression data to determine their emotional state. This emotion recognition evaluates the driver's emotions, such as joy, surprise, anger, sadness, and stress. The emotion engine then comprehensively evaluates this information to infer the driver's attention level and psychological state.

[0316] Based on the extracted features and sentiment analysis results, the server estimates the driver's drowsiness level and issues an immediate warning if necessary. The warning is adjusted according to the driver's emotional state; for example, if the driver is stressed, a milder warning will be issued.

[0317] For example, if the driver's eyes start opening and closing slowly during long-distance driving, and they also appear irritated, the system will provide a voice and display warning such as, "Drowsiness has been detected. Please take a short break and relax." This allows the driver to recognize their condition early and take appropriate actions for safe driving.

[0318] In this way, the system can comprehensively monitor the driver's drowsiness and emotions, providing a safety function that helps prevent traffic accidents.

[0319] The following describes the processing flow.

[0320] Step 1:

[0321] The terminal uses cameras installed inside the vehicle to acquire video data of the driver. This video data is transmitted to the server in real time.

[0322] Step 2:

[0323] The server uses a face detection algorithm to identify the driver's face from the received video data. The identified face is then tracked to stably acquire continuous data.

[0324] Step 3:

[0325] The server extracts features such as eye opening / closing status, blinking frequency, face orientation, and head tilt from the face it tracks. This data is used to analyze drowsiness.

[0326] Step 4:

[0327] The server uses an emotion engine to analyze the driver's emotional state from their facial expressions. This analysis evaluates emotions such as joy, surprise, anger, sadness, and stress that the driver is experiencing.

[0328] Step 5:

[0329] The server estimates the driver's drowsiness level based on extracted features and sentiment analysis results. It then checks whether the drowsiness score exceeds a pre-set threshold.

[0330] Step 6:

[0331] The server creates the most appropriate warning for the driver based on the estimated drowsiness score and emotional state. If the result is deemed dangerous, a warning signal is sent to the terminal.

[0332] Step 7:

[0333] The terminal receives a warning signal from the server and issues a warning to the user. The warning is delivered via audio or visual means, and its content is tailored to best suit the driver's condition.

[0334] (Example 2)

[0335] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0336] During long drives or in monotonous driving environments, driver drowsiness and psychological fatigue are often contributing factors to accidents. However, conventional systems are insufficient to accurately monitor drowsiness and emotional states and provide timely warnings to drivers. Therefore, there is a need for a system that can detect driver drowsiness and emotional states with high accuracy and support safe driving.

[0337] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0338] In this invention, the server includes means for analyzing and tracking the driver's video information in real time, means for extracting drowsiness-related feature data from the driver's face, and means for analyzing the emotional state from the facial expression data. This makes it possible to estimate the driver's drowsiness level and emotional state with high accuracy and issue appropriate warnings.

[0339] A "video input device" is a device used to acquire video information of the driver and has the function of providing video data in real time.

[0340] "Analysis" refers to the process of determining the driver's condition based on video information and facial expression data.

[0341] "Tracking" is a technology that monitors the driver's posture and behavior by continuously tracking detected facial movements.

[0342] "Characteristic data" refers to specific data related to drowsiness and the driver's condition, such as eye opening and closing, blinking frequency, face orientation, and head tilt.

[0343] "Drowsiness level" is an index that quantifies or grades the driver's level of alertness.

[0344] "Facial expression data" refers to information about the driver's facial expressions, which is used to determine their emotional state.

[0345] "Emotional state" refers to the driver's mental reactions and psychological condition, including joy, surprise, anger, sadness, and stress.

[0346] A "warning" refers to an audible or visual signal issued to draw the driver's attention or provide advice.

[0347] This invention is a system for detecting the drowsiness and emotional state of a vehicle driver with high accuracy and supporting safe driving. This system consists of a terminal installed inside the vehicle and a server that analyzes video data.

[0348] The terminal acquires video information of the driver using the vehicle's cameras. For this purpose, it uses a high-resolution camera mounted on the terminal. The camera records video data in real time and transmits it to a server via a high-speed communication network such as Wi-Fi or 5G.

[0349] The server uses the received video data and an AI facial recognition library to identify and continuously track the driver's face. Libraries such as OpenCV and Dlib are used in this process. The server then extracts drowsiness-related feature data, such as eye opening / closing status, blinking frequency, face orientation, and head tilt.

[0350] Furthermore, the server is equipped with an emotion recognition engine that uses a deep learning model to analyze the driver's emotional state from facial expression data. Frameworks such as TensorFlow and PyTorch are commonly used. Emotion analysis is performed to evaluate the driver's psychological state, including joy, surprise, anger, sadness, and stress.

[0351] By comprehensively analyzing this data, the server estimates the driver's level of drowsiness and issues a warning if necessary. The warning is generated using speech synthesis technology and communicated to the driver audibly or visually. For example, if the driver blinks slowly and shows signs of stress during long-distance driving, the server will warn, "Drowsiness detected. Please take a short break and relax."

[0352] An example of a prompt to a generative AI model is: "Please tell me how to analyze the driver's eye opening / closing state and facial expression based on image data to evaluate drowsiness and emotional state."

[0353] In this way, the system of the present invention can monitor the driver's condition with high precision and provide a safety function that prevents traffic accidents.

[0354] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0355] Step 1:

[0356] The terminal acquires video information of the driver through a camera installed inside the vehicle. The camera is adjusted to capture the driver's face clearly at high resolution. The input is raw video data acquired by the camera, which is then encoded and converted to an appropriate format. The output is video data in a transmittable format.

[0357] Step 2:

[0358] The device sends encoded video data to the server. This communication takes place using a Wi-Fi or 5G network, and the data is transferred with low latency. The input is the encoded video data, and the output is the video data delivered to the server.

[0359] Step 3:

[0360] The server analyzes the video data received from the terminal and detects the driver's face using AI facial recognition software. An open-source facial recognition library is used to extract the face's location information. The input is the received video data, and the output is the driver's face location information.

[0361] Step 4:

[0362] The server tracks detected facial movements and extracts sleepiness-related feature data such as eye opening / closing status, blinking frequency, face orientation, and head tilt. Image processing libraries are used for this process. The input is facial position information, and the output is sleepiness-related feature data.

[0363] Step 5:

[0364] The server analyzes the driver's emotional state based on extracted feature data. It uses a deep learning model to classify emotions from facial expression data. The input is feature data, and the output is information about the emotional state.

[0365] Step 6:

[0366] The server comprehensively evaluates the driver's drowsiness level and emotional state, and generates a warning to the driver as needed. Natural language processing techniques are used for this warning generation. The input is the drowsiness level and emotional state, and the output is a warning message to the driver.

[0367] Step 7:

[0368] Warning messages sent from the server are notified to the user via the terminal. The warning messages are played aloud using speech synthesis technology. The input is the warning message, and the output is either an audio or visual warning.

[0369] (Application Example 2)

[0370] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0371] Responding quickly to driver drowsiness and changes in emotional state to support safe driving is a crucial challenge. In particular, it is necessary to adjust the environment appropriately according to the driver's psychological state to reduce fatigue and stress. Conventional systems have the problem that they can only monitor drowsiness and emotional state individually, making it difficult to provide comprehensive safe driving support.

[0372] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0373] In this invention, the server includes means for acquiring video information of the operator from a video input device, means for detecting and tracking the operator's face in real time based on the video information, means for extracting characteristic information related to drowsiness from the detected operator's face, and means for adjusting the environment based on the operator's emotional state. This makes it possible to comprehensively judge the driver's drowsiness and emotional state in real time and provide appropriate warnings and environmental adjustments.

[0374] A "video input device" is a device that captures the operator's face and surrounding environment in real time and acquires that video information.

[0375] "Operator" refers to a person who operates a vehicle or machine.

[0376] "Tracking" refers to the continuous monitoring of the detected face's position and movement.

[0377] "Characteristic information" refers to specific data extracted from the pilot's face that indicates drowsiness and emotional state.

[0378] "Sleepiness level" refers to the pilot's state of alertness and is a scale used to assess how much attention is required in that state.

[0379] "Notification" refers to the act of a system communicating warnings or information to the operator through audio or video.

[0380] "Environmental adjustment" refers to modifying environmental elements such as the sound and lighting inside the vehicle according to the driver's psychological state.

[0381] To implement this invention, it is necessary to acquire video footage of the driver using a camera placed inside the vehicle and transmit that data to a server. The server uses OpenCV as its video processing library to perform real-time facial recognition and tracking of the driver. Furthermore, it extracts features and analyzes the driver's emotional state using an emotion analysis API such as AWS Rekognition. Based on this data, the server estimates the driver's level of drowsiness and emotional state and issues a warning if necessary.

[0382] Furthermore, the in-vehicle infotainment system automatically adjusts the sound and lighting according to the driver's state. This program helps reduce stress while driving and supports safe driving.

[0383] For example, if the driver's blinking frequency increases during long-distance driving and emotional analysis detects fatigue, the system will issue a voice warning saying, "Take a short break and refresh yourself." It can also change the interior lighting to a softer color and play relaxing music.

[0384] An example of a prompt message might be: "Please write a program that analyzes the pilot's drowsiness and emotions in real time using video data, and generates rest suggestions based on the pilot's condition."

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] The terminal uses a camera installed inside the vehicle to capture video of the driver. The input is the camera feed, and the output is this video data. At this stage, the video is captured in real time.

[0388] Step 2:

[0389] The server receives video data transmitted from the terminal. The input is the video data from the terminal, and the output is the video data prepared for analysis. In this process, the server verifies the integrity of the data transfer.

[0390] Step 3:

[0391] The server uses OpenCV to detect and track the operator's face in real time from video data. The input is video data, and the output is the operator's facial feature points. This process involves identifying the detected coordinates of the face and continuously tracking it.

[0392] Step 4:

[0393] The server extracts sleepiness-related feature information from the detected faces. The input is facial feature points, and the output is information such as eye open / closed state and blinking frequency. This process generates specific indicators of sleepiness.

[0394] Step 5:

[0395] The server uses an emotion analysis API to analyze the operator's emotional state from extracted facial data. The input is facial feature information, and the output is the operator's emotional state. Here, the emotion engine identifies states such as joy and stress.

[0396] Step 6:

[0397] The server comprehensively assesses the degree of drowsiness and emotional state, and issues notifications to the pilot as needed. Input is information about drowsiness and emotions, and output is the notification content. If a warning is required, it will be communicated to the pilot via voice or display.

[0398] Step 7:

[0399] The server adjusts the in-vehicle environment (sound and lighting) according to the driver's state. The input is the driver's emotional state, and the output is the adjusted environmental settings. This process optimizes the environment to improve driving comfort.

[0400] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0401] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0402] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0403] [Third Embodiment]

[0404] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0405] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0406] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0407] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0408] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0409] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0410] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0411] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0412] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0413] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0414] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0415] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0416] The system of this invention consists of a terminal mounted in the vehicle and a server that performs analysis in a central location. The terminal includes a drive recorder, which includes a camera as a video input means for capturing images of the driver inside the vehicle. The video data is transmitted to the server in real time and analyzed there.

[0417] The server detects the driver's face from the received video data and continuously tracks the identified face. During this process, it extracts features such as the driver's eye opening / closing state, blinking frequency, face orientation, and head tilt. These features are treated as important data because they may indicate signs of drowsiness.

[0418] Based on the extracted features, a generative AI model on the server estimates the driver's drowsiness level. This estimate is quantified as a drowsiness score and compared to a set threshold. If the threshold is exceeded, the server sends a warning signal to the terminal.

[0419] The terminal receives warning signals from the server and issues warnings to the user (driver) in an audible or visual manner. For example, this can be done using voice alerts or warning displays on the dashboard. This helps the user become aware of drowsiness and encourages them to take a break at an appropriate time.

[0420] For example, if the system detects an increase in the driver's blinking frequency while driving on a highway for extended periods, it can immediately issue a warning, alerting the driver to the long time since their last break and encouraging them to take a safe rest.

[0421] Such a system can reduce the risk of accidents caused by drowsiness while driving and provide a safer driving environment.

[0422] The following describes the processing flow.

[0423] Step 1:

[0424] The device acquires video data via the in-car camera. The acquired video data is transmitted to the server in real time.

[0425] Step 2:

[0426] The server detects the driver's face from the received video data. To perform face detection, a machine learning algorithm is applied to identify the location of the person's face in the video.

[0427] Step 3:

[0428] The server tracks the identified face. It continuously tracks facial movements and corrects for changes in face size and position to obtain stable data.

[0429] Step 4:

[0430] The server extracts features from the facial tracking results. It extracts data that serves as an indicator for determining drowsiness, such as the state of eye opening and closing, blinking frequency, face direction, and head tilt.

[0431] Step 5:

[0432] The server estimates the drowsiness level based on the extracted features. A generative AI model is used to analyze the features and calculate a drowsiness score.

[0433] Step 6:

[0434] The server calculates a drowsiness score and compares it to a set threshold. If the score exceeds the threshold, it is determined that there are signs of drowsiness.

[0435] Step 7:

[0436] If the server detects signs of drowsiness, it sends a warning signal to the terminal.

[0437] Step 8:

[0438] The device issues a warning to the user based on the warning signal it receives. The warning is given using audio alerts or visual displays. The user receives the warning and is prompted to stop the vehicle and take a break if necessary.

[0439] (Example 1)

[0440] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0441] During long drives or in monotonous road conditions, drivers can easily become drowsy. However, drowsiness can lead to delayed reactions and falling asleep at the wheel, increasing the risk of serious traffic accidents. Therefore, there is a need for methods to maintain safe driving by detecting drowsiness early and providing appropriate warnings to drivers.

[0442] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0443] In this invention, the server includes means for collecting video information of vehicle users obtained from a video acquisition device, means for continuously recognizing and tracking the faces of vehicle users based on the video information, and means for extracting characteristic information related to drowsiness from the faces of recognized vehicle users. This makes it possible to quickly and accurately detect signs of drowsiness while driving and to immediately issue a warning to the driver.

[0444] A "video acquisition device" is a device installed inside or outside a vehicle to collect image information of the driver.

[0445] "Vehicle user" refers to an individual who operates or uses a vehicle, and in this invention, it primarily means the driver.

[0446] "Video information" refers to image data obtained by video acquisition devices, and is fundamental data for analyzing the driver's actions and behavior.

[0447] "Recognition and tracking" refers to the technology of detecting a specific object from collected video information and continuously analyzing its location and movement.

[0448] "Characteristic information" refers to measurable data related to the driver's level of drowsiness and attention, extracted from the driver's video footage, and includes, for example, eye opening and closing patterns and blinking frequency.

[0449] "Means for evaluating drowsiness" refers to a function that quantifies and estimates the driver's current level of attention and alertness based on extracted characteristic information.

[0450] A "warning" is a visual or audible notification signal issued to draw the driver's attention.

[0451] An embodiment of this invention is a system consisting of a terminal mounted in a vehicle and a central server. The terminal functions as a video acquisition device and collects video information of vehicle users. For example, a camera installed inside the vehicle may be used as the terminal. This camera captures the driver's face and upper body and acquires video data in real time. The terminal transmits this data to the server via Wi-Fi or mobile communication.

[0452] The server analyzes the transmitted video information using open-source image processing libraries. First, it detects the faces of vehicle users from the video information and continuously tracks them using a specific algorithm. Face landmark detection technology is utilized for face recognition and tracking. Next, the server extracts feature information based on the movement and state of the face. This feature information is an important indicator for evaluating driver drowsiness and includes specific data such as eye opening and closing and head tilt.

[0453] Based on the extracted feature information, the server uses a generative AI model to evaluate the driver's drowsiness level. This AI model is pre-trained using machine learning and can estimate the likelihood of drowsiness with high accuracy. If the evaluated drowsiness score exceeds a set threshold, the server sends an alert to the terminal. This alert is communicated to the user via acoustic or visual signals. For example, an audio alert may be played from the speaker, or a message such as "Please be careful" may be displayed on the dashboard display.

[0454] An example of a prompt message would be, "Detect the driver's face from the video data while driving and analyze signs of drowsiness." This allows the system to monitor the driver's condition and improve driving safety.

[0455] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0456] Step 1:

[0457] The terminal acquires real-time video data of the driver using a camera installed inside the vehicle. The camera's angle is adjusted to capture the driver's face and upper body. The input consists of continuous image frames acquired from the camera sensor. The output is video data ready for transmission to the server.

[0458] Step 2:

[0459] The terminal transmits the acquired video data to the server via the network. Wi-Fi or cellular communication is used for communication, and the data may be temporarily buffered. The input is the video data obtained in step 1, and the output is the video data received by the server.

[0460] Step 3:

[0461] The server detects the driver's face from the received video data. Here, a video processing library is used to recognize the facial contours and landmarks. The input is video data transmitted from the terminal, and the output is data containing facial position information. Specifically, an image analysis algorithm is applied.

[0462] Step 4:

[0463] The server extracts feature information such as eye opening / closing status, blinking frequency, face orientation, and head tilt from the detected face location data. This process analyzes variations between frames and extracts specific patterns. The input is face location data, and the output is feature information used for drowsiness estimation.

[0464] Step 5:

[0465] The server inputs the extracted feature information into a generating AI model to estimate the driver's drowsiness level. The AI ​​model generates a drowsiness score based on pre-trained data. The input is feature information, and the output is data quantified as a drowsiness score.

[0466] Step 6:

[0467] The server compares the estimated drowsiness score to a set threshold and sends an alarm signal to the terminal if necessary. Here, the threshold is pre-set as a threshold to maintain safe driving. The input is the drowsiness score, and the output is the instruction to send an alarm signal.

[0468] Step 7:

[0469] The terminal receives alarm signals from the server and issues warnings to the user (driver) via audio and visual signals. These warnings may include messages displayed on the dashboard or alerts from the speaker. The input is the alarm signal from the server, and the output is the alarm perceived by the user.

[0470] (Application Example 1)

[0471] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0472] In today's traffic society, accidents caused by driver drowsiness remain a serious problem. To address this issue, there is a need for technology that can monitor drivers' conditions in real time, predict drowsiness, and prompt them to take appropriate breaks. Furthermore, there is a lack of information available to help drivers take breaks efficiently. A system that solves this problem is needed.

[0473] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0474] In this invention, the server includes means for acquiring video data of the driver obtained from a video input means, means for detecting and tracking the driver's face in real time based on the video data, means for extracting features related to drowsiness from the detected driver's face, and means for suggesting the next rest stop based on the driver's state. This makes it possible to reduce the risk of accidents caused by driver drowsiness and provide information to enable the driver to rest efficiently.

[0475] "Video input means" refers to a device or method used to acquire video data of the driver.

[0476] A "device that detects and tracks the driver's face in real time" is a technology that continuously identifies the position and movement of the driver's face in real time based on video data of the driver.

[0477] "Characteristics related to drowsiness" refer to facial features and movements that may suggest drowsiness, such as the state of the driver's eyes (open and closed), blinking frequency, face orientation, and head tilt.

[0478] A "device for estimating a driver's drowsiness level" is a system that analyzes extracted features to determine the driver's level of drowsiness.

[0479] A "warning device" is a means of providing a signal to the driver to alert them based on an estimated level of drowsiness.

[0480] A "device that suggests the next rest stop based on the driver's condition" is an information provision system that takes into account the driver's current level of drowsiness and shows the driver the optimal rest location and time.

[0481] To implement this invention, a system is required that utilizes a terminal mounted on the vehicle and a server for analysis. The terminal includes a camera as a means of video input and acquires video data of the driver. This data is transmitted to the server in real time. The server uses a generated AI model to detect the driver's face from the received video data and tracks it in real time. Through face tracking, features related to drowsiness are extracted, including the state of eye opening and closing, blinking frequency, face orientation, and head tilt.

[0482] The server runs a generative AI model that estimates the driver's drowsiness level based on these features. If the estimated drowsiness level exceeds a threshold, the server sends a warning signal to the terminal. This warning is communicated to the driver using audio and visual signals.

[0483] The system also includes a feature that suggests the next rest stop based on the driver's level of drowsiness. The server calculates the optimal rest stop based on location and road information and provides this information to the device. This information is displayed on the driver's smartphone or the vehicle's display.

[0484] For example, if a driver blinks more frequently while driving for an extended period, the server will determine that the driver is becoming drowsy. In this case, a message such as, "You appear to be tired while driving. How about taking a break at the next rest stop?" can be sent to the terminal, and a nearby service area can be displayed on the map to encourage the driver to take a break.

[0485] Examples of prompt statements include the following:

[0486] "Design a system that analyzes driver drowsiness in real time and prompts rest as needed."

[0487] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0488] Step 1:

[0489] The terminal uses a camera installed inside the vehicle to acquire video data of the driver. The video data is transmitted to the server in real time. The input is the raw video from the camera, and the output is the digital video data transmitted to the server.

[0490] Step 2:

[0491] The server analyzes the received video data and uses a generative AI model to detect the driver's face. The AI ​​model has a pre-installed face recognition algorithm that extracts specific facial features from the video data. The input is video data, and the output is a dataset containing the face detection results.

[0492] Step 3:

[0493] The server extracts features related to drowsiness from the detected faces. Specifically, it uses an AI model to calculate eye open / closed states, blinking frequency, face orientation, and head tilt. The input is the face detection result, and the output is data containing these features.

[0494] Step 4:

[0495] The server estimates the driver's drowsiness level based on extracted features. The AI ​​model evaluates multiple features and calculates a drowsiness score. The input is feature data, and the output is the drowsiness score.

[0496] Step 5:

[0497] If the generated drowsiness score exceeds a set threshold, the server sends a warning signal to the terminal. This includes a trigger signal to alert the driver. The input is the drowsiness score, and the output is the warning signal.

[0498] Step 6:

[0499] The device uses the received warning signal to send audio and visual warnings to the driver. Specific actions include outputting an audio alert from the speaker and displaying a warning message on the screen. The input is the warning signal, and the output is feedback to the user.

[0500] Step 7:

[0501] The server calculates information about the next rest stop based on the driver's current drowsiness level and sends it to the terminal. This involves combining GPS data and road information to determine an appropriate rest stop. The input is drowsiness level and location information, and the output is suggested rest stop information.

[0502] Step 8:

[0503] The device notifies the driver of the received rest stop information and displays accessible rest stops on a map. Specifically, it displays a map showing rest stops on the smartphone or vehicle's display. The input is suggested rest stop information, and the output is visual information for the user.

[0504] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0505] This invention provides a system that accurately detects a driver's drowsiness and emotional state, thereby supporting safe driving. The system consists of a terminal installed in the vehicle and a server that analyzes video data.

[0506] The terminal uses the vehicle's cameras to acquire video data of the driver. This video data is transmitted to the server in real time. Based on the received video data, the server detects and continuously tracks the driver's face. In this process, features related to drowsiness, such as eye opening and closing, blinking frequency, face orientation, and head tilt, are extracted.

[0507] Furthermore, the server is equipped with an emotion engine that analyzes the driver's facial expression data to determine their emotional state. This emotion recognition evaluates the driver's emotions, such as joy, surprise, anger, sadness, and stress. The emotion engine then comprehensively evaluates this information to infer the driver's attention level and psychological state.

[0508] Based on the extracted features and sentiment analysis results, the server estimates the driver's drowsiness level and issues an immediate warning if necessary. The warning is adjusted according to the driver's emotional state; for example, if the driver is stressed, a milder warning will be issued.

[0509] For example, if the driver's eyes start opening and closing slowly during long-distance driving, and they also appear irritated, the system will provide a voice and display warning such as, "Drowsiness has been detected. Please take a short break and relax." This allows the driver to recognize their condition early and take appropriate actions for safe driving.

[0510] In this way, the system can comprehensively monitor the driver's drowsiness and emotions, providing a safety function that helps prevent traffic accidents.

[0511] The following describes the processing flow.

[0512] Step 1:

[0513] The terminal uses cameras installed inside the vehicle to acquire video data of the driver. This video data is transmitted to the server in real time.

[0514] Step 2:

[0515] The server uses a face detection algorithm to identify the driver's face from the received video data. The identified face is then tracked to stably acquire continuous data.

[0516] Step 3:

[0517] The server extracts features such as eye opening / closing status, blinking frequency, face orientation, and head tilt from the face it tracks. This data is used to analyze drowsiness.

[0518] Step 4:

[0519] The server uses an emotion engine to analyze the driver's emotional state from their facial expressions. This analysis evaluates emotions such as joy, surprise, anger, sadness, and stress that the driver is experiencing.

[0520] Step 5:

[0521] The server estimates the driver's drowsiness level based on extracted features and sentiment analysis results. It then checks whether the drowsiness score exceeds a pre-set threshold.

[0522] Step 6:

[0523] The server creates the most appropriate warning for the driver based on the estimated drowsiness score and emotional state. If the result is deemed dangerous, a warning signal is sent to the terminal.

[0524] Step 7:

[0525] The terminal receives a warning signal from the server and issues a warning to the user. The warning is delivered via audio or visual means, and its content is tailored to best suit the driver's condition.

[0526] (Example 2)

[0527] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0528] During long drives or in monotonous driving environments, driver drowsiness and psychological fatigue are often contributing factors to accidents. However, conventional systems are insufficient to accurately monitor drowsiness and emotional states and provide timely warnings to drivers. Therefore, there is a need for a system that can detect driver drowsiness and emotional states with high accuracy and support safe driving.

[0529] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0530] In this invention, the server includes means for analyzing and tracking the driver's video information in real time, means for extracting drowsiness-related feature data from the driver's face, and means for analyzing the emotional state from the facial expression data. This makes it possible to estimate the driver's drowsiness level and emotional state with high accuracy and issue appropriate warnings.

[0531] A "video input device" is a device used to acquire video information of the driver and has the function of providing video data in real time.

[0532] "Analysis" refers to the process of determining the driver's condition based on video information and facial expression data.

[0533] "Tracking" is a technology that monitors the driver's posture and behavior by continuously tracking detected facial movements.

[0534] "Characteristic data" refers to specific data related to drowsiness and the driver's condition, such as eye opening and closing, blinking frequency, face orientation, and head tilt.

[0535] "Drowsiness level" is an index that quantifies or grades the driver's level of alertness.

[0536] "Facial expression data" refers to information about the driver's facial expressions, which is used to determine their emotional state.

[0537] "Emotional state" refers to the driver's mental reactions and psychological condition, including joy, surprise, anger, sadness, and stress.

[0538] A "warning" refers to an audible or visual signal issued to draw the driver's attention or provide advice.

[0539] This invention is a system for detecting the drowsiness and emotional state of a vehicle driver with high accuracy and supporting safe driving. This system consists of a terminal installed inside the vehicle and a server that analyzes video data.

[0540] The terminal acquires video information of the driver using the vehicle's cameras. For this purpose, it uses a high-resolution camera mounted on the terminal. The camera records video data in real time and transmits it to a server via a high-speed communication network such as Wi-Fi or 5G.

[0541] The server uses the received video data and an AI facial recognition library to identify and continuously track the driver's face. Libraries such as OpenCV and Dlib are used in this process. The server then extracts drowsiness-related feature data, such as eye opening / closing status, blinking frequency, face orientation, and head tilt.

[0542] Furthermore, the server is equipped with an emotion recognition engine that uses a deep learning model to analyze the driver's emotional state from facial expression data. Frameworks such as TensorFlow and PyTorch are commonly used. Emotion analysis is performed to evaluate the driver's psychological state, including joy, surprise, anger, sadness, and stress.

[0543] By comprehensively analyzing this data, the server estimates the driver's level of drowsiness and issues a warning if necessary. The warning is generated using speech synthesis technology and communicated to the driver audibly or visually. For example, if the driver blinks slowly and shows signs of stress during long-distance driving, the server will warn, "Drowsiness detected. Please take a short break and relax."

[0544] An example of a prompt to a generative AI model is: "Please tell me how to analyze the driver's eye opening / closing state and facial expression based on image data to evaluate drowsiness and emotional state."

[0545] In this way, the system of the present invention can monitor the driver's condition with high precision and provide a safety function that prevents traffic accidents.

[0546] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0547] Step 1:

[0548] The terminal acquires video information of the driver through a camera installed inside the vehicle. The camera is adjusted to capture the driver's face clearly at high resolution. The input is raw video data acquired by the camera, which is then encoded and converted to an appropriate format. The output is video data in a transmittable format.

[0549] Step 2:

[0550] The device sends encoded video data to the server. This communication takes place using a Wi-Fi or 5G network, and the data is transferred with low latency. The input is the encoded video data, and the output is the video data delivered to the server.

[0551] Step 3:

[0552] The server analyzes the video data received from the terminal and detects the driver's face using AI facial recognition software. An open-source facial recognition library is used to extract the face's location information. The input is the received video data, and the output is the driver's face location information.

[0553] Step 4:

[0554] The server tracks detected facial movements and extracts sleepiness-related feature data such as eye opening / closing status, blinking frequency, face orientation, and head tilt. Image processing libraries are used for this process. The input is facial position information, and the output is sleepiness-related feature data.

[0555] Step 5:

[0556] The server analyzes the driver's emotional state based on extracted feature data. It uses a deep learning model to classify emotions from facial expression data. The input is feature data, and the output is information about the emotional state.

[0557] Step 6:

[0558] The server comprehensively evaluates the driver's drowsiness level and emotional state, and generates a warning to the driver as needed. Natural language processing techniques are used for this warning generation. The input is the drowsiness level and emotional state, and the output is a warning message to the driver.

[0559] Step 7:

[0560] Warning messages sent from the server are notified to the user via the terminal. The warning messages are played aloud using speech synthesis technology. The input is the warning message, and the output is either an audio or visual warning.

[0561] (Application Example 2)

[0562] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0563] Responding quickly to driver drowsiness and changes in emotional state to support safe driving is a crucial challenge. In particular, it is necessary to adjust the environment appropriately according to the driver's psychological state to reduce fatigue and stress. Conventional systems have the problem that they can only monitor drowsiness and emotional state individually, making it difficult to provide comprehensive safe driving support.

[0564] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0565] In this invention, the server includes means for acquiring video information of the operator from a video input device, means for detecting and tracking the operator's face in real time based on the video information, means for extracting characteristic information related to drowsiness from the detected operator's face, and means for adjusting the environment based on the operator's emotional state. This makes it possible to comprehensively judge the driver's drowsiness and emotional state in real time and provide appropriate warnings and environmental adjustments.

[0566] A "video input device" is a device that captures the operator's face and surrounding environment in real time and acquires that video information.

[0567] "Operator" refers to a person who operates a vehicle or machine.

[0568] "Tracking" refers to the continuous monitoring of the detected face's position and movement.

[0569] "Characteristic information" refers to specific data extracted from the pilot's face that indicates drowsiness and emotional state.

[0570] "Sleepiness level" refers to the pilot's state of alertness and is a scale used to assess how much attention is required in that state.

[0571] "Notification" refers to the act of a system communicating warnings or information to the operator through audio or video.

[0572] "Environmental adjustment" refers to modifying environmental elements such as the sound and lighting inside the vehicle according to the driver's psychological state.

[0573] To implement this invention, it is necessary to acquire video footage of the driver using a camera placed inside the vehicle and transmit that data to a server. The server uses OpenCV as its video processing library to perform real-time facial recognition and tracking of the driver. Furthermore, it extracts features and analyzes the driver's emotional state using an emotion analysis API such as AWS Rekognition. Based on this data, the server estimates the driver's level of drowsiness and emotional state and issues a warning if necessary.

[0574] Furthermore, the in-vehicle infotainment system automatically adjusts the sound and lighting according to the driver's state. This program helps reduce stress while driving and supports safe driving.

[0575] For example, if the driver's blinking frequency increases during long-distance driving and emotional analysis detects fatigue, the system will issue a voice warning saying, "Take a short break and refresh yourself." It can also change the interior lighting to a softer color and play relaxing music.

[0576] An example of a prompt message might be: "Please write a program that analyzes the pilot's drowsiness and emotions in real time using video data, and generates rest suggestions based on the pilot's condition."

[0577] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0578] Step 1:

[0579] The terminal uses a camera installed inside the vehicle to capture video of the driver. The input is the camera feed, and the output is this video data. At this stage, the video is captured in real time.

[0580] Step 2:

[0581] The server receives video data transmitted from the terminal. The input is the video data from the terminal, and the output is the video data prepared for analysis. In this process, the server verifies the integrity of the data transfer.

[0582] Step 3:

[0583] The server uses OpenCV to detect and track the operator's face in real time from video data. The input is video data, and the output is the operator's facial feature points. This process involves identifying the detected coordinates of the face and continuously tracking it.

[0584] Step 4:

[0585] The server extracts sleepiness-related feature information from the detected faces. The input is facial feature points, and the output is information such as eye open / closed state and blinking frequency. This process generates specific indicators of sleepiness.

[0586] Step 5:

[0587] The server uses an emotion analysis API to analyze the operator's emotional state from extracted facial data. The input is facial feature information, and the output is the operator's emotional state. Here, the emotion engine identifies states such as joy and stress.

[0588] Step 6:

[0589] The server comprehensively assesses the degree of drowsiness and emotional state, and issues notifications to the pilot as needed. Input is information about drowsiness and emotions, and output is the notification content. If a warning is required, it will be communicated to the pilot via voice or display.

[0590] Step 7:

[0591] The server adjusts the in-vehicle environment (sound and lighting) according to the driver's state. The input is the driver's emotional state, and the output is the adjusted environmental settings. This process optimizes the environment to improve driving comfort.

[0592] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0593] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0594] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0595] [Fourth Embodiment]

[0596] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0597] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0598] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0599] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0600] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0601] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0602] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0603] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0604] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0605] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0606] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0607] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0608] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0609] The system of this invention consists of a terminal mounted in the vehicle and a server that performs analysis in a central location. The terminal includes a drive recorder, which includes a camera as a video input means for capturing images of the driver inside the vehicle. The video data is transmitted to the server in real time and analyzed there.

[0610] The server detects the driver's face from the received video data and continuously tracks the identified face. During this process, it extracts features such as the driver's eye opening / closing state, blinking frequency, face orientation, and head tilt. These features are treated as important data because they may indicate signs of drowsiness.

[0611] Based on the extracted features, a generative AI model on the server estimates the driver's drowsiness level. This estimate is quantified as a drowsiness score and compared to a set threshold. If the threshold is exceeded, the server sends a warning signal to the terminal.

[0612] The terminal receives warning signals from the server and issues warnings to the user (driver) in an audible or visual manner. For example, this can be done using voice alerts or warning displays on the dashboard. This helps the user become aware of drowsiness and encourages them to take a break at an appropriate time.

[0613] For example, if the system detects an increase in the driver's blinking frequency while driving on a highway for extended periods, it can immediately issue a warning, alerting the driver to the long time since their last break and encouraging them to take a safe rest.

[0614] Such a system can reduce the risk of accidents caused by drowsiness while driving and provide a safer driving environment.

[0615] The following describes the processing flow.

[0616] Step 1:

[0617] The device acquires video data via the in-car camera. The acquired video data is transmitted to the server in real time.

[0618] Step 2:

[0619] The server detects the driver's face from the received video data. To perform face detection, a machine learning algorithm is applied to identify the location of the person's face in the video.

[0620] Step 3:

[0621] The server tracks the identified face. It continuously tracks facial movements and corrects for changes in face size and position to obtain stable data.

[0622] Step 4:

[0623] The server extracts features from the facial tracking results. It extracts data that serves as an indicator for determining drowsiness, such as the state of eye opening and closing, blinking frequency, face direction, and head tilt.

[0624] Step 5:

[0625] The server estimates the drowsiness level based on the extracted features. A generative AI model is used to analyze the features and calculate a drowsiness score.

[0626] Step 6:

[0627] The server calculates a drowsiness score and compares it to a set threshold. If the score exceeds the threshold, it is determined that there are signs of drowsiness.

[0628] Step 7:

[0629] If the server detects signs of drowsiness, it sends a warning signal to the terminal.

[0630] Step 8:

[0631] The device issues a warning to the user based on the warning signal it receives. The warning is given using audio alerts or visual displays. The user receives the warning and is prompted to stop the vehicle and take a break if necessary.

[0632] (Example 1)

[0633] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0634] During long drives or in monotonous road conditions, drivers can easily become drowsy. However, drowsiness can lead to delayed reactions and falling asleep at the wheel, increasing the risk of serious traffic accidents. Therefore, there is a need for methods to maintain safe driving by detecting drowsiness early and providing appropriate warnings to drivers.

[0635] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0636] In this invention, the server includes means for collecting video information of vehicle users obtained from a video acquisition device, means for continuously recognizing and tracking the faces of vehicle users based on the video information, and means for extracting characteristic information related to drowsiness from the faces of recognized vehicle users. This makes it possible to quickly and accurately detect signs of drowsiness while driving and to immediately issue a warning to the driver.

[0637] A "video acquisition device" is a device installed inside or outside a vehicle to collect image information of the driver.

[0638] "Vehicle user" refers to an individual who operates or uses a vehicle, and in this invention, it primarily means the driver.

[0639] "Video information" refers to image data obtained by video acquisition devices, and is fundamental data for analyzing the driver's actions and behavior.

[0640] "Recognition and tracking" refers to the technology of detecting a specific object from collected video information and continuously analyzing its location and movement.

[0641] "Characteristic information" refers to measurable data related to the driver's level of drowsiness and attention, extracted from the driver's video footage, and includes, for example, eye opening and closing patterns and blinking frequency.

[0642] "Means for evaluating drowsiness" refers to a function that quantifies and estimates the driver's current level of attention and alertness based on extracted characteristic information.

[0643] A "warning" is a visual or audible notification signal issued to draw the driver's attention.

[0644] An embodiment of this invention is a system consisting of a terminal mounted in a vehicle and a central server. The terminal functions as a video acquisition device and collects video information of vehicle users. For example, a camera installed inside the vehicle may be used as the terminal. This camera captures the driver's face and upper body and acquires video data in real time. The terminal transmits this data to the server via Wi-Fi or mobile communication.

[0645] The server analyzes the transmitted video information using open-source image processing libraries. First, it detects the faces of vehicle users from the video information and continuously tracks them using a specific algorithm. Face landmark detection technology is utilized for face recognition and tracking. Next, the server extracts feature information based on the movement and state of the face. This feature information is an important indicator for evaluating driver drowsiness and includes specific data such as eye opening and closing and head tilt.

[0646] Based on the extracted feature information, the server uses a generative AI model to evaluate the driver's drowsiness level. This AI model is pre-trained using machine learning and can estimate the likelihood of drowsiness with high accuracy. If the evaluated drowsiness score exceeds a set threshold, the server sends an alert to the terminal. This alert is communicated to the user via acoustic or visual signals. For example, an audio alert may be played from the speaker, or a message such as "Please be careful" may be displayed on the dashboard display.

[0647] An example of a prompt message would be, "Detect the driver's face from the video data while driving and analyze signs of drowsiness." This allows the system to monitor the driver's condition and improve driving safety.

[0648] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0649] Step 1:

[0650] The terminal acquires real-time video data of the driver using a camera installed inside the vehicle. The camera's angle is adjusted to capture the driver's face and upper body. The input consists of continuous image frames acquired from the camera sensor. The output is video data ready for transmission to the server.

[0651] Step 2:

[0652] The terminal transmits the acquired video data to the server via the network. Wi-Fi or cellular communication is used for communication, and the data may be temporarily buffered. The input is the video data obtained in step 1, and the output is the video data received by the server.

[0653] Step 3:

[0654] The server detects the driver's face from the received video data. Here, a video processing library is used to recognize the facial contours and landmarks. The input is video data transmitted from the terminal, and the output is data containing facial position information. Specifically, an image analysis algorithm is applied.

[0655] Step 4:

[0656] The server extracts feature information such as eye opening / closing status, blinking frequency, face orientation, and head tilt from the detected face location data. This process analyzes variations between frames and extracts specific patterns. The input is face location data, and the output is feature information used for drowsiness estimation.

[0657] Step 5:

[0658] The server inputs the extracted feature information into a generating AI model to estimate the driver's drowsiness level. The AI ​​model generates a drowsiness score based on pre-trained data. The input is feature information, and the output is data quantified as a drowsiness score.

[0659] Step 6:

[0660] The server compares the estimated drowsiness score to a set threshold and sends an alarm signal to the terminal if necessary. Here, the threshold is pre-set as a threshold to maintain safe driving. The input is the drowsiness score, and the output is the instruction to send an alarm signal.

[0661] Step 7:

[0662] The terminal receives alarm signals from the server and issues warnings to the user (driver) via audio and visual signals. These warnings may include messages displayed on the dashboard or alerts from the speaker. The input is the alarm signal from the server, and the output is the alarm perceived by the user.

[0663] (Application Example 1)

[0664] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0665] In today's traffic society, accidents caused by driver drowsiness remain a serious problem. To address this issue, there is a need for technology that can monitor drivers' conditions in real time, predict drowsiness, and prompt them to take appropriate breaks. Furthermore, there is a lack of information available to help drivers take breaks efficiently. A system that solves this problem is needed.

[0666] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0667] In this invention, the server includes means for acquiring video data of the driver obtained from a video input means, means for detecting and tracking the driver's face in real time based on the video data, means for extracting features related to drowsiness from the detected driver's face, and means for suggesting the next rest stop based on the driver's state. This makes it possible to reduce the risk of accidents caused by driver drowsiness and provide information to enable the driver to rest efficiently.

[0668] "Video input means" refers to a device or method used to acquire video data of the driver.

[0669] A "device that detects and tracks the driver's face in real time" is a technology that continuously identifies the position and movement of the driver's face in real time based on video data of the driver.

[0670] "Characteristics related to drowsiness" refer to facial features and movements that may suggest drowsiness, such as the state of the driver's eyes (open and closed), blinking frequency, face orientation, and head tilt.

[0671] A "device for estimating a driver's drowsiness level" is a system that analyzes extracted features to determine the driver's level of drowsiness.

[0672] A "warning device" is a means of providing a signal to the driver to alert them based on an estimated level of drowsiness.

[0673] A "device that suggests the next rest stop based on the driver's condition" is an information provision system that takes into account the driver's current level of drowsiness and shows the driver the optimal rest location and time.

[0674] To implement this invention, a system is required that utilizes a terminal mounted on the vehicle and a server for analysis. The terminal includes a camera as a means of video input and acquires video data of the driver. This data is transmitted to the server in real time. The server uses a generated AI model to detect the driver's face from the received video data and tracks it in real time. Through face tracking, features related to drowsiness are extracted, including the state of eye opening and closing, blinking frequency, face orientation, and head tilt.

[0675] The server runs a generative AI model that estimates the driver's drowsiness level based on these features. If the estimated drowsiness level exceeds a threshold, the server sends a warning signal to the terminal. This warning is communicated to the driver using audio and visual signals.

[0676] The system also includes a feature that suggests the next rest stop based on the driver's level of drowsiness. The server calculates the optimal rest stop based on location and road information and provides this information to the device. This information is displayed on the driver's smartphone or the vehicle's display.

[0677] For example, if a driver blinks more frequently while driving for an extended period, the server will determine that the driver is becoming drowsy. In this case, a message such as, "You appear to be tired while driving. How about taking a break at the next rest stop?" can be sent to the terminal, and a nearby service area can be displayed on the map to encourage the driver to take a break.

[0678] Examples of prompt statements include the following:

[0679] "Design a system that analyzes driver drowsiness in real time and prompts rest as needed."

[0680] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0681] Step 1:

[0682] The terminal uses a camera installed inside the vehicle to acquire video data of the driver. The video data is transmitted to the server in real time. The input is the raw video from the camera, and the output is the digital video data transmitted to the server.

[0683] Step 2:

[0684] The server analyzes the received video data and uses a generative AI model to detect the driver's face. The AI ​​model has a pre-installed face recognition algorithm that extracts specific facial features from the video data. The input is video data, and the output is a dataset containing the face detection results.

[0685] Step 3:

[0686] The server extracts features related to drowsiness from the detected faces. Specifically, it uses an AI model to calculate eye open / closed states, blinking frequency, face orientation, and head tilt. The input is the face detection result, and the output is data containing these features.

[0687] Step 4:

[0688] The server estimates the driver's drowsiness level based on extracted features. The AI ​​model evaluates multiple features and calculates a drowsiness score. The input is feature data, and the output is the drowsiness score.

[0689] Step 5:

[0690] If the generated drowsiness score exceeds a set threshold, the server sends a warning signal to the terminal. This includes a trigger signal to alert the driver. The input is the drowsiness score, and the output is the warning signal.

[0691] Step 6:

[0692] The device uses the received warning signal to send audio and visual warnings to the driver. Specific actions include outputting an audio alert from the speaker and displaying a warning message on the screen. The input is the warning signal, and the output is feedback to the user.

[0693] Step 7:

[0694] The server calculates information about the next rest stop based on the driver's current drowsiness level and sends it to the terminal. This involves combining GPS data and road information to determine an appropriate rest stop. The input is drowsiness level and location information, and the output is suggested rest stop information.

[0695] Step 8:

[0696] The device notifies the driver of the received rest stop information and displays accessible rest stops on a map. Specifically, it displays a map showing rest stops on the smartphone or vehicle's display. The input is suggested rest stop information, and the output is visual information for the user.

[0697] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0698] This invention provides a system that accurately detects a driver's drowsiness and emotional state, thereby supporting safe driving. The system consists of a terminal installed in the vehicle and a server that analyzes video data.

[0699] The terminal uses the vehicle's cameras to acquire video data of the driver. This video data is transmitted to the server in real time. Based on the received video data, the server detects and continuously tracks the driver's face. In this process, features related to drowsiness, such as eye opening and closing, blinking frequency, face orientation, and head tilt, are extracted.

[0700] Furthermore, the server is equipped with an emotion engine that analyzes the driver's facial expression data to determine their emotional state. This emotion recognition evaluates the driver's emotions, such as joy, surprise, anger, sadness, and stress. The emotion engine then comprehensively evaluates this information to infer the driver's attention level and psychological state.

[0701] Based on the extracted features and sentiment analysis results, the server estimates the driver's drowsiness level and issues an immediate warning if necessary. The warning is adjusted according to the driver's emotional state; for example, if the driver is stressed, a milder warning will be issued.

[0702] For example, if the driver's eyes start opening and closing slowly during long-distance driving, and they also appear irritated, the system will provide a voice and display warning such as, "Drowsiness has been detected. Please take a short break and relax." This allows the driver to recognize their condition early and take appropriate actions for safe driving.

[0703] In this way, the system can comprehensively monitor the driver's drowsiness and emotions, providing a safety function that helps prevent traffic accidents.

[0704] The following describes the processing flow.

[0705] Step 1:

[0706] The terminal uses cameras installed inside the vehicle to acquire video data of the driver. This video data is transmitted to the server in real time.

[0707] Step 2:

[0708] The server uses a face detection algorithm to identify the driver's face from the received video data. The identified face is then tracked to stably acquire continuous data.

[0709] Step 3:

[0710] The server extracts features such as eye opening / closing status, blinking frequency, face orientation, and head tilt from the face it tracks. This data is used to analyze drowsiness.

[0711] Step 4:

[0712] The server uses an emotion engine to analyze the driver's emotional state from their facial expressions. This analysis evaluates emotions such as joy, surprise, anger, sadness, and stress that the driver is experiencing.

[0713] Step 5:

[0714] The server estimates the driver's drowsiness level based on extracted features and sentiment analysis results. It then checks whether the drowsiness score exceeds a pre-set threshold.

[0715] Step 6:

[0716] The server creates the most appropriate warning for the driver based on the estimated drowsiness score and emotional state. If the result is deemed dangerous, a warning signal is sent to the terminal.

[0717] Step 7:

[0718] The terminal receives a warning signal from the server and issues a warning to the user. The warning is delivered via audio or visual means, and its content is tailored to best suit the driver's condition.

[0719] (Example 2)

[0720] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0721] During long drives or in monotonous driving environments, driver drowsiness and psychological fatigue are often contributing factors to accidents. However, conventional systems are insufficient to accurately monitor drowsiness and emotional states and provide timely warnings to drivers. Therefore, there is a need for a system that can detect driver drowsiness and emotional states with high accuracy and support safe driving.

[0722] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0723] In this invention, the server includes means for analyzing and tracking the driver's video information in real time, means for extracting drowsiness-related feature data from the driver's face, and means for analyzing the emotional state from the facial expression data. This makes it possible to estimate the driver's drowsiness level and emotional state with high accuracy and issue appropriate warnings.

[0724] A "video input device" is a device used to acquire video information of the driver and has the function of providing video data in real time.

[0725] "Analysis" refers to the process of determining the driver's condition based on video information and facial expression data.

[0726] "Tracking" is a technology that monitors the driver's posture and behavior by continuously tracking detected facial movements.

[0727] "Characteristic data" refers to specific data related to drowsiness and the driver's condition, such as eye opening and closing, blinking frequency, face orientation, and head tilt.

[0728] "Drowsiness level" is an index that quantifies or grades the driver's level of alertness.

[0729] "Facial expression data" refers to information about the driver's facial expressions, which is used to determine their emotional state.

[0730] "Emotional state" refers to the driver's mental reactions and psychological condition, including joy, surprise, anger, sadness, and stress.

[0731] A "warning" refers to an audible or visual signal issued to draw the driver's attention or provide advice.

[0732] This invention is a system for detecting the drowsiness and emotional state of a vehicle driver with high accuracy and supporting safe driving. This system consists of a terminal installed inside the vehicle and a server that analyzes video data.

[0733] The terminal acquires video information of the driver using the vehicle's cameras. For this purpose, it uses a high-resolution camera mounted on the terminal. The camera records video data in real time and transmits it to a server via a high-speed communication network such as Wi-Fi or 5G.

[0734] The server uses the received video data and an AI facial recognition library to identify and continuously track the driver's face. Libraries such as OpenCV and Dlib are used in this process. The server then extracts drowsiness-related feature data, such as eye opening / closing status, blinking frequency, face orientation, and head tilt.

[0735] Furthermore, the server is equipped with an emotion recognition engine that uses a deep learning model to analyze the driver's emotional state from facial expression data. Frameworks such as TensorFlow and PyTorch are commonly used. Emotion analysis is performed to evaluate the driver's psychological state, including joy, surprise, anger, sadness, and stress.

[0736] By comprehensively analyzing this data, the server estimates the driver's level of drowsiness and issues a warning if necessary. The warning is generated using speech synthesis technology and communicated to the driver audibly or visually. For example, if the driver blinks slowly and shows signs of stress during long-distance driving, the server will warn, "Drowsiness detected. Please take a short break and relax."

[0737] An example of a prompt to a generative AI model is: "Please tell me how to analyze the driver's eye opening / closing state and facial expression based on image data to evaluate drowsiness and emotional state."

[0738] In this way, the system of the present invention can monitor the driver's condition with high precision and provide a safety function that prevents traffic accidents.

[0739] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0740] Step 1:

[0741] The terminal acquires video information of the driver through a camera installed inside the vehicle. The camera is adjusted to capture the driver's face clearly at high resolution. The input is raw video data acquired by the camera, which is then encoded and converted to an appropriate format. The output is video data in a transmittable format.

[0742] Step 2:

[0743] The device sends encoded video data to the server. This communication takes place using a Wi-Fi or 5G network, and the data is transferred with low latency. The input is the encoded video data, and the output is the video data delivered to the server.

[0744] Step 3:

[0745] The server analyzes the video data received from the terminal and detects the driver's face using AI facial recognition software. An open-source facial recognition library is used to extract the face's location information. The input is the received video data, and the output is the driver's face location information.

[0746] Step 4:

[0747] The server tracks detected facial movements and extracts sleepiness-related feature data such as eye opening / closing status, blinking frequency, face orientation, and head tilt. Image processing libraries are used for this process. The input is facial position information, and the output is sleepiness-related feature data.

[0748] Step 5:

[0749] The server analyzes the driver's emotional state based on extracted feature data. It uses a deep learning model to classify emotions from facial expression data. The input is feature data, and the output is information about the emotional state.

[0750] Step 6:

[0751] The server comprehensively evaluates the driver's drowsiness level and emotional state, and generates a warning to the driver as needed. Natural language processing techniques are used for this warning generation. The input is the drowsiness level and emotional state, and the output is a warning message to the driver.

[0752] Step 7:

[0753] Warning messages sent from the server are notified to the user via the terminal. The warning messages are played aloud using speech synthesis technology. The input is the warning message, and the output is either an audio or visual warning.

[0754] (Application Example 2)

[0755] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0756] Responding quickly to driver drowsiness and changes in emotional state to support safe driving is a crucial challenge. In particular, it is necessary to adjust the environment appropriately according to the driver's psychological state to reduce fatigue and stress. Conventional systems have the problem that they can only monitor drowsiness and emotional state individually, making it difficult to provide comprehensive safe driving support.

[0757] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0758] In this invention, the server includes means for acquiring video information of the operator from a video input device, means for detecting and tracking the operator's face in real time based on the video information, means for extracting characteristic information related to drowsiness from the detected operator's face, and means for adjusting the environment based on the operator's emotional state. This makes it possible to comprehensively judge the driver's drowsiness and emotional state in real time and provide appropriate warnings and environmental adjustments.

[0759] A "video input device" is a device that captures the operator's face and surrounding environment in real time and acquires that video information.

[0760] "Operator" refers to a person who operates a vehicle or machine.

[0761] "Tracking" refers to the continuous monitoring of the detected face's position and movement.

[0762] "Characteristic information" refers to specific data extracted from the pilot's face that indicates drowsiness and emotional state.

[0763] "Sleepiness level" refers to the pilot's state of alertness and is a scale used to assess how much attention is required in that state.

[0764] "Notification" refers to the act of a system communicating warnings or information to the operator through audio or video.

[0765] "Environmental adjustment" refers to modifying environmental elements such as the sound and lighting inside the vehicle according to the driver's psychological state.

[0766] To implement this invention, it is necessary to acquire video footage of the driver using a camera placed inside the vehicle and transmit that data to a server. The server uses OpenCV as its video processing library to perform real-time facial recognition and tracking of the driver. Furthermore, it extracts features and analyzes the driver's emotional state using an emotion analysis API such as AWS Rekognition. Based on this data, the server estimates the driver's level of drowsiness and emotional state and issues a warning if necessary.

[0767] Furthermore, the in-vehicle infotainment system automatically adjusts the sound and lighting according to the driver's state. This program helps reduce stress while driving and supports safe driving.

[0768] For example, if the driver's blinking frequency increases during long-distance driving and emotional analysis detects fatigue, the system will issue a voice warning saying, "Take a short break and refresh yourself." It can also change the interior lighting to a softer color and play relaxing music.

[0769] An example of a prompt message might be: "Please write a program that analyzes the pilot's drowsiness and emotions in real time using video data, and generates rest suggestions based on the pilot's condition."

[0770] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0771] Step 1:

[0772] The terminal uses a camera installed inside the vehicle to capture video of the driver. The input is the camera feed, and the output is this video data. At this stage, the video is captured in real time.

[0773] Step 2:

[0774] The server receives video data transmitted from the terminal. The input is the video data from the terminal, and the output is the video data prepared for analysis. In this process, the server verifies the integrity of the data transfer.

[0775] Step 3:

[0776] The server uses OpenCV to detect and track the operator's face in real time from video data. The input is video data, and the output is the operator's facial feature points. This process involves identifying the detected coordinates of the face and continuously tracking it.

[0777] Step 4:

[0778] The server extracts sleepiness-related feature information from the detected faces. The input is facial feature points, and the output is information such as eye open / closed state and blinking frequency. This process generates specific indicators of sleepiness.

[0779] Step 5:

[0780] The server uses an emotion analysis API to analyze the operator's emotional state from extracted facial data. The input is facial feature information, and the output is the operator's emotional state. Here, the emotion engine identifies states such as joy and stress.

[0781] Step 6:

[0782] The server comprehensively assesses the degree of drowsiness and emotional state, and issues notifications to the pilot as needed. Input is information about drowsiness and emotions, and output is the notification content. If a warning is required, it will be communicated to the pilot via voice or display.

[0783] Step 7:

[0784] The server adjusts the in-vehicle environment (sound and lighting) according to the driver's state. The input is the driver's emotional state, and the output is the adjusted environmental settings. This process optimizes the environment to improve driving comfort.

[0785] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0786] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0787] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0788] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0789] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0790] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0791] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0792] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0793] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0794] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0795] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0796] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0797] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0798] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0799] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0800] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0801] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0802] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0803] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0804] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0805] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0806] The following is further disclosed regarding the embodiments described above.

[0807] (Claim 1)

[0808] A means for acquiring video data of the driver obtained from a video input means,

[0809] A means for detecting and tracking the driver's face in real time based on the video data,

[0810] A means for extracting features related to drowsiness from the detected driver's face,

[0811] A means for estimating the driver's drowsiness level based on extracted features,

[0812] A means for issuing a warning to the driver based on the estimation result,

[0813] A system that includes this.

[0814] (Claim 2)

[0815] The system according to claim 1, wherein the extracted features include the state of eye opening and closing, blinking frequency, face orientation, and head tilt.

[0816] (Claim 3)

[0817] The system according to claim 1, wherein the means for issuing a warning to the driver is to use an audio signal and a visual signal.

[0818] "Example 1"

[0819] (Claim 1)

[0820] A means for collecting video information of vehicle users obtained from a video acquisition device,

[0821] A means for continuously recognizing and tracking the faces of vehicle users based on the video information,

[0822] A means for extracting characteristic information related to drowsiness from the faces of recognized vehicle users,

[0823] A means for evaluating the drowsiness level of vehicle users based on extracted characteristic information,

[0824] A means of issuing a warning to the vehicle user based on the evaluation results,

[0825] A system that includes this.

[0826] (Claim 2)

[0827] The system according to claim 1, wherein the extracted feature information includes the state of eye opening and closing, blinking frequency, face orientation, and head tilt.

[0828] (Claim 3)

[0829] The system according to claim 1, wherein the means of issuing a warning to vehicle users is to use an audible signal and a visual signal.

[0830] "Application Example 1"

[0831] (Claim 1)

[0832] A device for acquiring driver video data obtained from a video input means,

[0833] A device that detects and tracks the driver's face in real time based on the video data,

[0834] A device that extracts features related to drowsiness from the detected face of the driver,

[0835] A device that estimates the driver's drowsiness level based on extracted features,

[0836] A device that issues a warning to the driver based on the estimation result,

[0837] A device that suggests the next rest stop based on the driver's condition,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, wherein the extracted features include the open / closed state of the visual organs, blinking frequency, face orientation, and head tilt.

[0841] (Claim 3)

[0842] The system according to claim 1, wherein the device that issues a warning to the driver uses an audio signal and a visual signal.

[0843] "Example 2 of combining an emotion engine"

[0844] (Claim 1)

[0845] A means for acquiring video information of the driver obtained from a video input device,

[0846] A means for analyzing and tracking the driver's face in real time based on the video information,

[0847] A means for extracting drowsiness-related feature data from the analyzed face of a driver,

[0848] A means for estimating the driver's drowsiness level based on extracted feature data,

[0849] A method for analyzing emotional states from the driver's facial expression data,

[0850] A means for issuing a warning to the driver based on the estimation result and the emotion analysis result,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, wherein the extracted feature data includes eye opening / closing states, blinking frequency, face orientation, and head tilt, and adjusts warnings according to emotional state.

[0854] (Claim 3)

[0855] The system according to claim 1, wherein the means of issuing a warning to the driver is to use an audible signal and a visual signal.

[0856] "Application example 2 of combining emotional engines"

[0857] (Claim 1)

[0858] A means for acquiring video information of the pilot obtained from a video input device,

[0859] A means for detecting and tracking the pilot's face in real time based on the video information,

[0860] A means for extracting characteristic information related to drowsiness from the detected face of the pilot,

[0861] A means for estimating the degree of pilot drowsiness based on extracted feature information,

[0862] A means for issuing a notification to the pilot based on the estimation result,

[0863] A means of adjusting the environment based on the pilot's emotional state,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, wherein the extracted feature information includes the state of eye opening and closing, blinking frequency, face orientation and head tilt, as well as emotional state.

[0867] (Claim 3)

[0868] The system according to claim 1, wherein the means for notifying the operator is to use audio signals, visual signals, and ambient sounds. [Explanation of Symbols]

[0869] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring video data of the driver obtained from a video input means, A means for detecting and tracking the driver's face in real time based on the video data, A means for extracting features related to drowsiness from the detected driver's face, A means for estimating the driver's drowsiness level based on extracted features, A means for issuing a warning to the driver based on the estimation result, A system that includes this.

2. The system according to claim 1, wherein the extracted features include the state of eye opening and closing, blinking frequency, face orientation, and head tilt.

3. The system according to claim 1, wherein the means for issuing a warning to the driver uses an audio signal and a visual signal.

Images